# MeshWalker: Deep Mesh Understanding by Random Walks

arXiv: https://arxiv.org/abs/2006.05353 · HTML: https://mlsanity.com/paper/2006.05353/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2020.

## Built on by (most cited first, 30 of 32)

- [Subdivision-Based Mesh Convolution Networks](https://mlsanity.com/paper/2106.02285/) (2021)
- [BuildingNet: Learning to Label 3D Buildings](https://mlsanity.com/paper/2110.04955/) (2021)
- [3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions](https://mlsanity.com/paper/2212.11263/) (2022)
- [S2O: Static to Openable Enhancement for Articulated 3D Objects](https://mlsanity.com/paper/2409.18896/) (2024)
- [A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation](https://mlsanity.com/paper/2405.11903/) (2024)
- [M"obius Convolutions for Spherical CNNs](https://mlsanity.com/paper/2201.12212/) (2022)
- [Laplacian2Mesh: Laplacian-Based Mesh Understanding](https://mlsanity.com/paper/2202.00307/) (2022)
- [DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds](https://mlsanity.com/paper/2111.08799/) (2021)
- [PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation](https://mlsanity.com/paper/2110.07882/) (2021)
- [DA Wand: Distortion-Aware Selection using Neural Mesh Parameterization](https://mlsanity.com/paper/2212.06344/) (2022)
- [A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Parts](https://mlsanity.com/paper/2410.14770/) (2024)
- [Bringing Attention to CAD: Boundary Representation Learning via Transformer](https://mlsanity.com/paper/2504.07134/) (2025)
- [ClothCombo: Modeling Inter-Cloth Interaction for Draping Multi-Layered Clothes](https://mlsanity.com/paper/2304.03492/) (2023)
- [Neural Shape Compiler: A Unified Framework for Transforming between Text, Point Cloud, and Program](https://mlsanity.com/paper/2212.12952/) (2022)
- [PoissonNet: A Local-Global Approach for Learning on Surfaces](https://mlsanity.com/paper/2510.14146/) (2025)
- [Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classification](https://mlsanity.com/paper/2106.15778/) (2021)
- [CloudWalker: Random walks for 3D point cloud shape analysis](https://mlsanity.com/paper/2112.01050/) (2021)
- [Be Careful with Rotation: A Uniform Backdoor Pattern for 3D Shape](https://mlsanity.com/paper/2211.16192/) (2022)
- [Random Walks for Adversarial Meshes](https://mlsanity.com/paper/2202.07453/) (2022)
- [PointNorm: Dual Normalization is All You Need for Point Cloud Analysis](https://mlsanity.com/paper/2207.06324/) (2022)
- [MeT: A Graph Transformer for Semantic Segmentation of 3D Meshes](https://mlsanity.com/paper/2307.01115/) (2023)
- [HodgeFormer: Transformers for Learnable Operators on Triangular Meshes through Data-Driven Hodge Matrices](https://mlsanity.com/paper/2509.01839/) (2025)
- [Interpolated SelectionConv for Spherical Images and Surfaces](https://mlsanity.com/paper/2210.10123/) (2022)
- [A Recipe for Geometry-Aware 3D Mesh Transformers](https://mlsanity.com/paper/2411.00164/) (2024)
- [CageNet: A Meta-Framework for Learning on Wild Meshes](https://mlsanity.com/paper/2505.18772/) (2025)
- [Long Range Pooling for 3D Large-Scale Scene Understanding](https://mlsanity.com/paper/2301.06962/) (2023)
- [Self-Parameterization Based Multi-Resolution Mesh Convolution Networks](https://mlsanity.com/paper/2408.13762/) (2024)
- [INRet: A General Framework for Accurate Retrieval of INRs for Shapes](https://mlsanity.com/paper/2501.15722/) (2025)
- [MME: Mixture of Mesh Experts with Random Walk Transformer Gating](https://mlsanity.com/paper/2603.00828/) (2026)
- [A 3D mesh convolution-based autoencoder for geometry compression](https://mlsanity.com/paper/2603.02125/) (2026)

## Abstract (arXiv)

Most attempts to represent 3D shapes for deep learning have focused on volumetric grids, multi-view images and point clouds. In this paper we look at the most popular representation of 3D shapes in computer graphics - a triangular mesh - and ask how it can be utilized within deep learning. The few attempts to answer this question propose to adapt convolutions & pooling to suit Convolutional Neural Networks (CNNs). This paper proposes a very different approach, termed MeshWalker, to learn the shape directly from a given mesh. The key idea is to represent the mesh by random walks along the surface, which "explore" the mesh's geometry and topology. Each walk is organized as a list of vertices, which in some manner imposes regularity on the mesh. The walk is fed into a Recurrent Neural Network (RNN) that "remembers" the history of the walk. We show that our approach achieves state-of-the-art results for two fundamental shape analysis tasks: shape classification and semantic segmentation. Furthermore, even a very small number of examples suffices for learning. This is highly important, since large datasets of meshes are difficult to acquire.